Dynamic planning in hierarchical active inference

TL;DR

This paper explores dynamic planning within hierarchical active inference models, emphasizing biological plausibility, affordance exploitation, and hybrid representations, advancing understanding of complex, adaptive behaviors beyond traditional neural network approaches.

Contribution

It introduces a hierarchical active inference framework for dynamic planning, focusing on affordance understanding and hybrid representations, which is a novel approach in the field.

Findings

Hierarchical models improve planning in changing environments.

Hybrid representations offer new insights into active inference.

Comparison of recent design choices highlights effective strategies.

Abstract

By dynamic planning, we refer to the ability of the human brain to infer and impose motor trajectories related to cognitive decisions. A recent paradigm, active inference, brings fundamental insights into the adaptation of biological organisms, constantly striving to minimize prediction errors to restrict themselves to life-compatible states. Over the past years, many studies have shown how human and animal behaviors could be explained in terms of active inference - either as discrete decision-making or continuous motor control - inspiring innovative solutions in robotics and artificial intelligence. Still, the literature lacks a comprehensive outlook on effectively planning realistic actions in changing environments. Setting ourselves the goal of modeling complex tasks such as tool use, we delve into the topic of dynamic planning in active inference, keeping in mind two crucial aspects of biological behavior: the capacity to understand and exploit affordances for object manipulation, and to learn the hierarchical interactions between the self and the environment, including other agents. We start from a simple unit and gradually describe more advanced structures, comparing recently proposed design choices and providing basic examples. This study distances itself from traditional views centered on neural networks and reinforcement learning, and points toward a yet unexplored direction in active inference: hybrid representations in hierarchical models.